Researchers use ASCII art to elicit harmful responses from 5 major AI chatbots

Ars Technica 2024-03-15

Summary:

LLMs are trained to block harmful responses. Old-school images can override those rules.

Link:

https://arstechnica.com/?p=2010646

From feeds:

Cyberlaw » Ars Technica
Music and Digital Media » Ars Technica

Tags:

&

Authors:

Dan Goodin

Date tagged:

03/15/2024, 20:38

Date published:

03/15/2024, 20:17